axyseo 2.1.11 → 2.1.13

package/build/cjs/languageProcessing/researches/getFleschReadingScore.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"getFleschReadingScore.js","names":["_stripNumbers","_interopRequireDefault","require","_countSentences","_countWords","_countSyllables","_lodash","e","__esModule","default","getAverage","total","amount","DIFFICULTY","exports","NO_DATA","VERY_EASY","EASY","FAIRLY_EASY","OKAY","FAIRLY_DIFFICULT","DIFFICULT","VERY_DIFFICULT","getDifficulty","score","scoreConfiguration","borders","veryEasy","inRange","easy","fairlyEasy","okay","fairlyDifficult","difficult","getConfiguration","researcher","languageSpecificConfig","getConfig","defaultConfig","veryDifficult","scores","_default","paper","syllables","memoizedTokenizer","getHelper","languageSpecificConfiguration","text","getText","difficulty","stripNumbers","numberOfSentences","countSentences","numberOfWords","countWords","numberOfSyllables","countSyllables","averageWordsPerSentence","syllablesPer100Words","statistics","getScore","clamp"],"sources":["../../../../src/languageProcessing/researches/getFleschReadingScore.js"],"sourcesContent":["/** @module analyses/calculateFleschReading */\n\nimport stripNumbers from \"../helpers/sanitize/stripNumbers.js\";\nimport countSentences from \"../helpers/sentence/countSentences.js\";\nimport countWords from \"../helpers/word/countWords.js\";\nimport countSyllables from \"../helpers/syllables/countSyllables.js\";\nimport { clamp, inRange } from \"lodash\";\n\n/**\n * Calculates an average from a total and an amount\n *\n * @param {number} total The total.\n * @param {number} amount The amount.\n * @returns {number} The average from the total and the amount.\n */\nconst getAverage = function( total, amount ) {\n\treturn total / amount;\n};\n\n/**\n * The Flesch reading ease difficulty.\n * @readonly\n * @enum {number}\n */\nexport const DIFFICULTY = {\n\tNO_DATA: -1,\n\tVERY_EASY: 0,\n\tEASY: 1,\n\tFAIRLY_EASY: 2,\n\tOKAY: 3,\n\tFAIRLY_DIFFICULT: 4,\n\tDIFFICULT: 5,\n\tVERY_DIFFICULT: 6,\n};\n\n/**\n * Returns the Flesch reading ease difficulty based on the boundaries\n * defined in the score configuration.\n *\n * @param {number} score The Flesch reading ease score.\n * @param {Object} scoreConfiguration The score configuration.\n *\n * @returns {DIFFICULTY} The Flesch reading ease difficulty.\n */\nfunction getDifficulty( score, scoreConfiguration ) {\n\tif ( score >= scoreConfiguration.borders.veryEasy ) {\n\t\treturn DIFFICULTY.VERY_EASY;\n\t} else if ( inRange( score, scoreConfiguration.borders.easy, scoreConfiguration.borders.veryEasy ) ) {\n\t\treturn DIFFICULTY.EASY;\n\t} else if ( inRange( score, scoreConfiguration.borders.fairlyEasy, scoreConfiguration.borders.easy ) ) {\n\t\treturn DIFFICULTY.FAIRLY_EASY;\n\t} else if ( inRange( score, scoreConfiguration.borders.okay, scoreConfiguration.borders.fairlyEasy ) ) {\n\t\treturn DIFFICULTY.OKAY;\n\t} else if ( inRange( score, scoreConfiguration.borders.fairlyDifficult, scoreConfiguration.borders.okay ) ) {\n\t\treturn DIFFICULTY.FAIRLY_DIFFICULT;\n\t} else if ( inRange( score, scoreConfiguration.borders.difficult, scoreConfiguration.borders.fairlyDifficult ) ) {\n\t\treturn DIFFICULTY.DIFFICULT;\n\t}\n\n\treturn DIFFICULTY.VERY_DIFFICULT;\n}\n\n/**\n * Retrieves the scoring configuration defining the boundaries to use to\n * determine the Flesch reading ease difficulty.\n *\n * @param {Researcher} researcher The researcher.\n *\n * @returns {Object} The language specific scoring configuration, or the default configuration if not available.\n */\nfunction getConfiguration( researcher ) {\n\tconst languageSpecificConfig = researcher.getConfig( \"fleschReadingEaseScores\" );\n\tconst defaultConfig = {\n\t\tborders: {\n\t\t\tveryEasy: 90,\n\t\t\teasy: 80,\n\t\t\tfairlyEasy: 70,\n\t\t\tokay: 60,\n\t\t\tfairlyDifficult: 50,\n\t\t\tdifficult: 30,\n\t\t\tveryDifficult: 0,\n\t\t},\n\t\tscores: {\n\t\t\tveryEasy: 9,\n\t\t\teasy: 9,\n\t\t\tfairlyEasy: 9,\n\t\t\tokay: 9,\n\t\t\tfairlyDifficult: 6,\n\t\t\tdifficult: 3,\n\t\t\tveryDifficult: 3,\n\t\t},\n\t};\n\treturn languageSpecificConfig ? languageSpecificConfig : defaultConfig;\n}\n\n/**\n * This calculates the Flesch reading score for a given text.\n *\n * @param {Paper}       paper           The paper containing the text.\n * @param {Researcher}  researcher      The researcher.\n *\n * @returns {{ score: number, difficulty: DIFFICULTY }} The Flesch reading score.\n */\nexport default function( paper, researcher ) {\n\tconst syllables = researcher.getConfig( \"syllables\" );\n\tconst memoizedTokenizer = researcher.getHelper( \"memoizedTokenizer\" );\n\tconst languageSpecificConfiguration = getConfiguration( researcher );\n\n\tlet text = paper.getText();\n\tif ( text === \"\" ) {\n\t\t// A score of -1 signals to the code down the line that no valid FRE was calculated.\n\t\treturn {\n\t\t\tscore: -1,\n\t\t\tdifficulty: DIFFICULTY.NO_DATA,\n\t\t};\n\t}\n\n\ttext = stripNumbers( text );\n\n\tconst numberOfSentences = countSentences( text, memoizedTokenizer );\n\tconst numberOfWords = countWords( text );\n\n\t// Do not show the Flesch reading ease when there is not enough data for the FRE to make sense. Also used to prevent division by zero errors.\n\t// A score of -1 signals to the code down the line that no valid FRE was calculated.\n\tif ( numberOfSentences < 1 || numberOfWords <= 10 ) {\n\t\treturn {\n\t\t\tscore: -1,\n\t\t\tdifficulty: DIFFICULTY.NO_DATA,\n\t\t};\n\t}\n\n\tconst numberOfSyllables = countSyllables( text, syllables );\n\tconst averageWordsPerSentence = getAverage( numberOfWords, numberOfSentences );\n\tconst syllablesPer100Words = numberOfSyllables * ( 100 / numberOfWords );\n\tconst statistics = {\n\t\tnumberOfSentences,\n\t\tnumberOfWords,\n\t\tnumberOfSyllables,\n\t\taverageWordsPerSentence,\n\t\tsyllablesPer100Words,\n\t};\n\n\tconst getScore = researcher.getHelper( \"fleschReadingScore\" );\n\n\tconst score = clamp( getScore( statistics ), 0, 100 );\n\n\tconst difficulty = getDifficulty( score, languageSpecificConfiguration );\n\n\treturn { score, difficulty };\n}\n"],"mappings":";;;;;;;AAEA,IAAAA,aAAA,GAAAC,sBAAA,CAAAC,OAAA;AACA,IAAAC,eAAA,GAAAF,sBAAA,CAAAC,OAAA;AACA,IAAAE,WAAA,GAAAH,sBAAA,CAAAC,OAAA;AACA,IAAAG,eAAA,GAAAJ,sBAAA,CAAAC,OAAA;AACA,IAAAI,OAAA,GAAAJ,OAAA;AAAwC,SAAAD,uBAAAM,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AANxC;;AAQA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMG,UAAU,GAAG,SAAAA,CAAUC,KAAK,EAAEC,MAAM,EAAG;EAC5C,OAAOD,KAAK,GAAGC,MAAM;AACtB,CAAC;;AAED;AACA;AACA;AACA;AACA;AACO,MAAMC,UAAU,GAAAC,OAAA,CAAAD,UAAA,GAAG;EACzBE,OAAO,EAAE,CAAC,CAAC;EACXC,SAAS,EAAE,CAAC;EACZC,IAAI,EAAE,CAAC;EACPC,WAAW,EAAE,CAAC;EACdC,IAAI,EAAE,CAAC;EACPC,gBAAgB,EAAE,CAAC;EACnBC,SAAS,EAAE,CAAC;EACZC,cAAc,EAAE;AACjB,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASC,aAAaA,CAAEC,KAAK,EAAEC,kBAAkB,EAAG;EACnD,IAAKD,KAAK,IAAIC,kBAAkB,CAACC,OAAO,CAACC,QAAQ,EAAG;IACnD,OAAOd,UAAU,CAACG,SAAS;EAC5B,CAAC,MAAM,IAAK,IAAAY,eAAO,EAAEJ,KAAK,EAAEC,kBAAkB,CAACC,OAAO,CAACG,IAAI,EAAEJ,kBAAkB,CAACC,OAAO,CAACC,QAAS,CAAC,EAAG;IACpG,OAAOd,UAAU,CAACI,IAAI;EACvB,CAAC,MAAM,IAAK,IAAAW,eAAO,EAAEJ,KAAK,EAAEC,kBAAkB,CAACC,OAAO,CAACI,UAAU,EAAEL,kBAAkB,CAACC,OAAO,CAACG,IAAK,CAAC,EAAG;IACtG,OAAOhB,UAAU,CAACK,WAAW;EAC9B,CAAC,MAAM,IAAK,IAAAU,eAAO,EAAEJ,KAAK,EAAEC,kBAAkB,CAACC,OAAO,CAACK,IAAI,EAAEN,kBAAkB,CAACC,OAAO,CAACI,UAAW,CAAC,EAAG;IACtG,OAAOjB,UAAU,CAACM,IAAI;EACvB,CAAC,MAAM,IAAK,IAAAS,eAAO,EAAEJ,KAAK,EAAEC,kBAAkB,CAACC,OAAO,CAACM,eAAe,EAAEP,kBAAkB,CAACC,OAAO,CAACK,IAAK,CAAC,EAAG;IAC3G,OAAOlB,UAAU,CAACO,gBAAgB;EACnC,CAAC,MAAM,IAAK,IAAAQ,eAAO,EAAEJ,KAAK,EAAEC,kBAAkB,CAACC,OAAO,CAACO,SAAS,EAAER,kBAAkB,CAACC,OAAO,CAACM,eAAgB,CAAC,EAAG;IAChH,OAAOnB,UAAU,CAACQ,SAAS;EAC5B;EAEA,OAAOR,UAAU,CAACS,cAAc;AACjC;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASY,gBAAgBA,CAAEC,UAAU,EAAG;EACvC,MAAMC,sBAAsB,GAAGD,UAAU,CAACE,SAAS,CAAE,yBAA0B,CAAC;EAChF,MAAMC,aAAa,GAAG;IACrBZ,OAAO,EAAE;MACRC,QAAQ,EAAE,EAAE;MACZE,IAAI,EAAE,EAAE;MACRC,UAAU,EAAE,EAAE;MACdC,IAAI,EAAE,EAAE;MACRC,eAAe,EAAE,EAAE;MACnBC,SAAS,EAAE,EAAE;MACbM,aAAa,EAAE;IAChB,CAAC;IACDC,MAAM,EAAE;MACPb,QAAQ,EAAE,CAAC;MACXE,IAAI,EAAE,CAAC;MACPC,UAAU,EAAE,CAAC;MACbC,IAAI,EAAE,CAAC;MACPC,eAAe,EAAE,CAAC;MAClBC,SAAS,EAAE,CAAC;MACZM,aAAa,EAAE;IAChB;EACD,CAAC;EACD,OAAOH,sBAAsB,GAAGA,sBAAsB,GAAGE,aAAa;AACvE;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAAAG,SAAUC,KAAK,EAAEP,UAAU,EAAG;EAC5C,MAAMQ,SAAS,GAAGR,UAAU,CAACE,SAAS,CAAE,WAAY,CAAC;EACrD,MAAMO,iBAAiB,GAAGT,UAAU,CAACU,SAAS,CAAE,mBAAoB,CAAC;EACrE,MAAMC,6BAA6B,GAAGZ,gBAAgB,CAAEC,UAAW,CAAC;EAEpE,IAAIY,IAAI,GAAGL,KAAK,CAACM,OAAO,CAAC,CAAC;EAC1B,IAAKD,IAAI,KAAK,EAAE,EAAG;IAClB;IACA,OAAO;MACNvB,KAAK,EAAE,CAAC,CAAC;MACTyB,UAAU,EAAEpC,UAAU,CAACE;IACxB,CAAC;EACF;EAEAgC,IAAI,GAAG,IAAAG,qBAAY,EAAEH,IAAK,CAAC;EAE3B,MAAMI,iBAAiB,GAAG,IAAAC,uBAAc,EAAEL,IAAI,EAAEH,iBAAkB,CAAC;EACnE,MAAMS,aAAa,GAAG,IAAAC,mBAAU,EAAEP,IAAK,CAAC;;EAExC;EACA;EACA,IAAKI,iBAAiB,GAAG,CAAC,IAAIE,aAAa,IAAI,EAAE,EAAG;IACnD,OAAO;MACN7B,KAAK,EAAE,CAAC,CAAC;MACTyB,UAAU,EAAEpC,UAAU,CAACE;IACxB,CAAC;EACF;EAEA,MAAMwC,iBAAiB,GAAG,IAAAC,uBAAc,EAAET,IAAI,EAAEJ,SAAU,CAAC;EAC3D,MAAMc,uBAAuB,GAAG/C,UAAU,CAAE2C,aAAa,EAAEF,iBAAkB,CAAC;EAC9E,MAAMO,oBAAoB,GAAGH,iBAAiB,IAAK,GAAG,GAAGF,aAAa,CAAE;EACxE,MAAMM,UAAU,GAAG;IAClBR,iBAAiB;IACjBE,aAAa;IACbE,iBAAiB;IACjBE,uBAAuB;IACvBC;EACD,CAAC;EAED,MAAME,QAAQ,GAAGzB,UAAU,CAACU,SAAS,CAAE,oBAAqB,CAAC;EAE7D,MAAMrB,KAAK,GAAG,IAAAqC,aAAK,EAAED,QAAQ,CAAED,UAAW,CAAC,EAAE,CAAC,EAAE,GAAI,CAAC;EAErD,MAAMV,UAAU,GAAG1B,aAAa,CAAEC,KAAK,EAAEsB,6BAA8B,CAAC;EAExE,OAAO;IAAEtB,KAAK;IAAEyB;EAAW,CAAC;AAC7B","ignoreList":[]}

package/build/cjs/languageProcessing/researches/getKeywordDensity.js

@@ -0,0 +1,49 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = getKeyphraseDensity;
+exports.getKeywordDensity = getKeywordDensity;
+var _countWords = _interopRequireDefault(require("../helpers/word/countWords"));
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+/**
+ * Calculates the keyphrase density.
+ *
+ * @param {Paper} paper The paper containing keyphrase and text.
+ * @param {Researcher} researcher The researcher.
+ *
+ * @returns {number} The keyphrase density.
+ */
+function getKeyphraseDensity(paper, researcher) {
+  const getWordsCustomHelper = researcher.getHelper('getWordsCustomHelper');
+  let wordCount = 0;
+
+  // If there is a custom getWords helper, use its output for countWords.
+  if (getWordsCustomHelper) {
+    wordCount = getWordsCustomHelper(paper.getText()).length;
+  } else {
+    wordCount = (0, _countWords.default)(paper.getText());
+  }
+  if (wordCount === 0) {
+    return 0;
+  }
+  const keyphraseCount = researcher.getResearch('getKeyphraseCount');
+  return keyphraseCount.count / wordCount * 100;
+}
+
+/**
+ * Calculates the keyphrase density.
+ *
+ * @deprecated Use getKeyphraseDensity instead.
+ *
+ * @param {Paper} paper The paper containing keyphrase and text.
+ * @param {Researcher} researcher The researcher.
+ *
+ * @returns {number} The keyphrase density.
+ */
+function getKeywordDensity(paper, researcher) {
+  console.warn('This function is deprecated, use getKeyphraseDensity instead.');
+  return getKeyphraseDensity(paper, researcher);
+}
+//# sourceMappingURL=getKeywordDensity.js.map

package/build/cjs/languageProcessing/researches/getKeywordDensity.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"getKeywordDensity.js","names":["_countWords","_interopRequireDefault","require","e","__esModule","default","getKeyphraseDensity","paper","researcher","getWordsCustomHelper","getHelper","wordCount","getText","length","countWords","keyphraseCount","getResearch","count","getKeywordDensity","console","warn"],"sources":["../../../../src/languageProcessing/researches/getKeywordDensity.js"],"sourcesContent":["import countWords from '@axyseo/languageProcessing/helpers/word/countWords';\n\n/**\n * Calculates the keyphrase density.\n *\n * @param {Paper} paper The paper containing keyphrase and text.\n * @param {Researcher} researcher The researcher.\n *\n * @returns {number} The keyphrase density.\n */\nexport default function getKeyphraseDensity(paper, researcher) {\n  const getWordsCustomHelper = researcher.getHelper('getWordsCustomHelper');\n  let wordCount = 0;\n\n  // If there is a custom getWords helper, use its output for countWords.\n  if (getWordsCustomHelper) {\n    wordCount = getWordsCustomHelper(paper.getText()).length;\n  } else {\n    wordCount = countWords(paper.getText());\n  }\n\n  if (wordCount === 0) {\n    return 0;\n  }\n  const keyphraseCount = researcher.getResearch('getKeyphraseCount');\n\n  return (keyphraseCount.count / wordCount) * 100;\n}\n\n/**\n * Calculates the keyphrase density.\n *\n * @deprecated Use getKeyphraseDensity instead.\n *\n * @param {Paper} paper The paper containing keyphrase and text.\n * @param {Researcher} researcher The researcher.\n *\n * @returns {number} The keyphrase density.\n */\nexport function getKeywordDensity(paper, researcher) {\n  console.warn('This function is deprecated, use getKeyphraseDensity instead.');\n  return getKeyphraseDensity(paper, researcher);\n}\n"],"mappings":";;;;;;;AAAA,IAAAA,WAAA,GAAAC,sBAAA,CAAAC,OAAA;AAA4E,SAAAD,uBAAAE,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAE5E;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAASG,mBAAmBA,CAACC,KAAK,EAAEC,UAAU,EAAE;EAC7D,MAAMC,oBAAoB,GAAGD,UAAU,CAACE,SAAS,CAAC,sBAAsB,CAAC;EACzE,IAAIC,SAAS,GAAG,CAAC;;EAEjB;EACA,IAAIF,oBAAoB,EAAE;IACxBE,SAAS,GAAGF,oBAAoB,CAACF,KAAK,CAACK,OAAO,CAAC,CAAC,CAAC,CAACC,MAAM;EAC1D,CAAC,MAAM;IACLF,SAAS,GAAG,IAAAG,mBAAU,EAACP,KAAK,CAACK,OAAO,CAAC,CAAC,CAAC;EACzC;EAEA,IAAID,SAAS,KAAK,CAAC,EAAE;IACnB,OAAO,CAAC;EACV;EACA,MAAMI,cAAc,GAAGP,UAAU,CAACQ,WAAW,CAAC,mBAAmB,CAAC;EAElE,OAAQD,cAAc,CAACE,KAAK,GAAGN,SAAS,GAAI,GAAG;AACjD;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACO,SAASO,iBAAiBA,CAACX,KAAK,EAAEC,UAAU,EAAE;EACnDW,OAAO,CAACC,IAAI,CAAC,+DAA+D,CAAC;EAC7E,OAAOd,mBAAmB,CAACC,KAAK,EAAEC,UAAU,CAAC;AAC/C","ignoreList":[]}

package/build/cjs/languageProcessing/researches/getLinkStatistics.js

@@ -0,0 +1,56 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = _default;
+var _checkNofollow = _interopRequireDefault(require("../helpers/link/checkNofollow.js"));
+var _getAnchorsFromText = _interopRequireDefault(require("../helpers/link/getAnchorsFromText.js"));
+var _getLinkType = _interopRequireDefault(require("../helpers/link/getLinkType.js"));
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+/**
+ * Counts the links found in the text.
+ *
+ * @param {Paper} paper The paper object containing text, keyword and url.
+ *
+ * @returns {object} The object containing all linktypes.
+ * total: the total number of links found.
+ * internalTotal: the total number of links that are internal.
+ * internalDofollow: the internal links without a nofollow attribute.
+ * internalNofollow: the internal links with a nofollow attribute.
+ * externalTotal: the total number of links that are external.
+ * externalDofollow: the external links without a nofollow attribute.
+ * externalNofollow: the internal links with a dofollow attribute.
+ * otherTotal: all links that are not HTTP or HTTPS.
+ * otherDofollow: other links without a nofollow attribute.
+ * otherNofollow: other links with a nofollow attribute.
+ */
+function _default(paper) {
+  const anchors = (0, _getAnchorsFromText.default)(paper.getText());
+  /*
+   * We get the site's URL (e.g., https://yoast.com) or domain (e.g., yoast.com) from the paper.
+   * In case of WordPress, the variable is a URL. In case of Shopify, it is a domain.
+   */
+  const siteUrlOrDomain = paper.getPermalink();
+  const linkCount = {
+    total: anchors.length,
+    internalTotal: 0,
+    internalDofollow: 0,
+    internalNofollow: 0,
+    externalTotal: 0,
+    externalDofollow: 0,
+    externalNofollow: 0,
+    otherTotal: 0,
+    otherDofollow: 0,
+    otherNofollow: 0
+  };
+  for (let i = 0; i < anchors.length; i++) {
+    const currentAnchor = anchors[i];
+    const linkType = (0, _getLinkType.default)(currentAnchor, siteUrlOrDomain);
+    const linkFollow = (0, _checkNofollow.default)(currentAnchor);
+    linkCount[linkType + "Total"]++;
+    linkCount[linkType + linkFollow]++;
+  }
+  return linkCount;
+}
+//# sourceMappingURL=getLinkStatistics.js.map

package/build/cjs/languageProcessing/researches/getLinkStatistics.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"getLinkStatistics.js","names":["_checkNofollow","_interopRequireDefault","require","_getAnchorsFromText","_getLinkType","e","__esModule","default","_default","paper","anchors","getAnchors","getText","siteUrlOrDomain","getPermalink","linkCount","total","length","internalTotal","internalDofollow","internalNofollow","externalTotal","externalDofollow","externalNofollow","otherTotal","otherDofollow","otherNofollow","i","currentAnchor","linkType","getLinkType","linkFollow","checkNofollow"],"sources":["../../../../src/languageProcessing/researches/getLinkStatistics.js"],"sourcesContent":["import checkNofollow from \"../helpers/link/checkNofollow.js\";\nimport getAnchors from \"../helpers/link/getAnchorsFromText.js\";\nimport getLinkType from \"../helpers/link/getLinkType.js\";\n\n/**\n * Counts the links found in the text.\n *\n * @param {Paper} paper The paper object containing text, keyword and url.\n *\n * @returns {object} The object containing all linktypes.\n * total: the total number of links found.\n * internalTotal: the total number of links that are internal.\n * internalDofollow: the internal links without a nofollow attribute.\n * internalNofollow: the internal links with a nofollow attribute.\n * externalTotal: the total number of links that are external.\n * externalDofollow: the external links without a nofollow attribute.\n * externalNofollow: the internal links with a dofollow attribute.\n * otherTotal: all links that are not HTTP or HTTPS.\n * otherDofollow: other links without a nofollow attribute.\n * otherNofollow: other links with a nofollow attribute.\n */\nexport default function( paper ) {\n\tconst anchors = getAnchors( paper.getText() );\n\t/*\n\t * We get the site's URL (e.g., https://yoast.com) or domain (e.g., yoast.com) from the paper.\n\t * In case of WordPress, the variable is a URL. In case of Shopify, it is a domain.\n\t */\n\tconst siteUrlOrDomain = paper.getPermalink();\n\n\tconst linkCount = {\n\t\ttotal: anchors.length,\n\t\tinternalTotal: 0,\n\t\tinternalDofollow: 0,\n\t\tinternalNofollow: 0,\n\t\texternalTotal: 0,\n\t\texternalDofollow: 0,\n\t\texternalNofollow: 0,\n\t\totherTotal: 0,\n\t\totherDofollow: 0,\n\t\totherNofollow: 0,\n\t};\n\n\tfor ( let i = 0; i < anchors.length; i++ ) {\n\t\tconst currentAnchor = anchors[ i ];\n\n\t\tconst linkType = getLinkType( currentAnchor, siteUrlOrDomain );\n\t\tconst linkFollow = checkNofollow( currentAnchor );\n\n\t\tlinkCount[ linkType + \"Total\" ]++;\n\t\tlinkCount[ linkType + linkFollow ]++;\n\t}\n\n\treturn linkCount;\n}\n"],"mappings":";;;;;;AAAA,IAAAA,cAAA,GAAAC,sBAAA,CAAAC,OAAA;AACA,IAAAC,mBAAA,GAAAF,sBAAA,CAAAC,OAAA;AACA,IAAAE,YAAA,GAAAH,sBAAA,CAAAC,OAAA;AAAyD,SAAAD,uBAAAI,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAEzD;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAAAG,SAAUC,KAAK,EAAG;EAChC,MAAMC,OAAO,GAAG,IAAAC,2BAAU,EAAEF,KAAK,CAACG,OAAO,CAAC,CAAE,CAAC;EAC7C;AACD;AACA;AACA;EACC,MAAMC,eAAe,GAAGJ,KAAK,CAACK,YAAY,CAAC,CAAC;EAE5C,MAAMC,SAAS,GAAG;IACjBC,KAAK,EAAEN,OAAO,CAACO,MAAM;IACrBC,aAAa,EAAE,CAAC;IAChBC,gBAAgB,EAAE,CAAC;IACnBC,gBAAgB,EAAE,CAAC;IACnBC,aAAa,EAAE,CAAC;IAChBC,gBAAgB,EAAE,CAAC;IACnBC,gBAAgB,EAAE,CAAC;IACnBC,UAAU,EAAE,CAAC;IACbC,aAAa,EAAE,CAAC;IAChBC,aAAa,EAAE;EAChB,CAAC;EAED,KAAM,IAAIC,CAAC,GAAG,CAAC,EAAEA,CAAC,GAAGjB,OAAO,CAACO,MAAM,EAAEU,CAAC,EAAE,EAAG;IAC1C,MAAMC,aAAa,GAAGlB,OAAO,CAAEiB,CAAC,CAAE;IAElC,MAAME,QAAQ,GAAG,IAAAC,oBAAW,EAAEF,aAAa,EAAEf,eAAgB,CAAC;IAC9D,MAAMkB,UAAU,GAAG,IAAAC,sBAAa,EAAEJ,aAAc,CAAC;IAEjDb,SAAS,CAAEc,QAAQ,GAAG,OAAO,CAAE,EAAE;IACjCd,SAAS,CAAEc,QAAQ,GAAGE,UAAU,CAAE,EAAE;EACrC;EAEA,OAAOhB,SAAS;AACjB","ignoreList":[]}

package/build/cjs/languageProcessing/researches/getLinks.js

@@ -0,0 +1,23 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = _default;
+var _getAnchorsFromText = _interopRequireDefault(require("../helpers/link/getAnchorsFromText.js"));
+var _lodash = require("lodash");
+var _url = _interopRequireDefault(require("../helpers/url/url.js"));
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+/** @module analyses/getLinkStatistics */
+
+/**
+ * Checks a text for anchors and returns the number found.
+ *
+ * @param {Object} paper The paper to get the text from.
+ * @returns {Array} An array with the anchors
+ */
+function _default(paper) {
+  const anchors = (0, _getAnchorsFromText.default)(paper.getText());
+  return (0, _lodash.map)(anchors, _url.default.getFromAnchorTag);
+}
+//# sourceMappingURL=getLinks.js.map

package/build/cjs/languageProcessing/researches/getLinks.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"getLinks.js","names":["_getAnchorsFromText","_interopRequireDefault","require","_lodash","_url","e","__esModule","default","_default","paper","anchors","getAnchors","getText","map","url","getFromAnchorTag"],"sources":["../../../../src/languageProcessing/researches/getLinks.js"],"sourcesContent":["/** @module analyses/getLinkStatistics */\n\nimport getAnchors from \"../helpers/link/getAnchorsFromText.js\";\n\nimport { map } from \"lodash\";\nimport url from \"../helpers/url/url.js\";\n\n/**\n * Checks a text for anchors and returns the number found.\n *\n * @param {Object} paper The paper to get the text from.\n * @returns {Array} An array with the anchors\n */\nexport default function( paper ) {\n\tconst anchors = getAnchors( paper.getText() );\n\n\treturn map( anchors, url.getFromAnchorTag );\n}\n"],"mappings":";;;;;;AAEA,IAAAA,mBAAA,GAAAC,sBAAA,CAAAC,OAAA;AAEA,IAAAC,OAAA,GAAAD,OAAA;AACA,IAAAE,IAAA,GAAAH,sBAAA,CAAAC,OAAA;AAAwC,SAAAD,uBAAAI,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AALxC;;AAOA;AACA;AACA;AACA;AACA;AACA;AACe,SAAAG,SAAUC,KAAK,EAAG;EAChC,MAAMC,OAAO,GAAG,IAAAC,2BAAU,EAAEF,KAAK,CAACG,OAAO,CAAC,CAAE,CAAC;EAE7C,OAAO,IAAAC,WAAG,EAAEH,OAAO,EAAEI,YAAG,CAACC,gBAAiB,CAAC;AAC5C","ignoreList":[]}

package/build/cjs/languageProcessing/researches/getLongCenterAlignedTexts.js

@@ -0,0 +1,42 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = _default;
+/**
+ * The maximum allowed length of a center-aligned paragraph or heading in characters.
+ * @type {number}
+ */
+const MAX_CENTER_ALIGNED_LENGTH = 50;
+
+/**
+ * A regular expression to match heading tags.
+ * @type {RegExp}
+ */
+const HEADING_TAGS_REGEX = /^h[1-6]$/;
+
+/**
+ * Filters out all nodes that are center-aligned and longer than 50 characters (as defined in `MAX_CENTER_ALIGNED_LENGTH`).
+ * @param {Node[]} nodes An array of nodes.
+ * @returns {Node[]} An array containing all center-aligned nodes that are longer than 50 characters.
+ */
+function getLongCenterAlignedElements(nodes) {
+  return nodes.filter(node => {
+    const isCenterAligned = node.attributes.class instanceof Set && node.attributes.class.has("has-text-align-center");
+    return isCenterAligned && node.innerText().length > MAX_CENTER_ALIGNED_LENGTH;
+  });
+}
+
+/**
+ * Finds all paragraphs and headings that are center-aligned and longer than 50 characters (after stripping HTML tags).
+ * @param {Paper} paper The paper to analyze.
+ * @returns {Node[]} An array of nodes containing too long center-aligned paragraphs/headings.
+ */
+function _default(paper) {
+  const tree = paper.getTree();
+  const paragraphs = tree.findAll(node => node.name === "p");
+  const headings = tree.findAll(node => HEADING_TAGS_REGEX.test(node.name));
+  return getLongCenterAlignedElements(paragraphs.concat(headings));
+}
+//# sourceMappingURL=getLongCenterAlignedTexts.js.map

package/build/cjs/languageProcessing/researches/getLongCenterAlignedTexts.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"getLongCenterAlignedTexts.js","names":["MAX_CENTER_ALIGNED_LENGTH","HEADING_TAGS_REGEX","getLongCenterAlignedElements","nodes","filter","node","isCenterAligned","attributes","class","Set","has","innerText","length","_default","paper","tree","getTree","paragraphs","findAll","name","headings","test","concat"],"sources":["../../../../src/languageProcessing/researches/getLongCenterAlignedTexts.js"],"sourcesContent":["/**\n * The maximum allowed length of a center-aligned paragraph or heading in characters.\n * @type {number}\n */\nconst MAX_CENTER_ALIGNED_LENGTH = 50;\n\n/**\n * A regular expression to match heading tags.\n * @type {RegExp}\n */\nconst HEADING_TAGS_REGEX = /^h[1-6]$/;\n\n/**\n * Filters out all nodes that are center-aligned and longer than 50 characters (as defined in `MAX_CENTER_ALIGNED_LENGTH`).\n * @param {Node[]} nodes An array of nodes.\n * @returns {Node[]} An array containing all center-aligned nodes that are longer than 50 characters.\n */\nfunction getLongCenterAlignedElements( nodes ) {\n\treturn nodes.filter( node => {\n\t\tconst isCenterAligned = node.attributes.class instanceof Set && node.attributes.class.has( \"has-text-align-center\" );\n\t\treturn isCenterAligned && node.innerText().length > MAX_CENTER_ALIGNED_LENGTH;\n\t} );\n}\n\n/**\n * Finds all paragraphs and headings that are center-aligned and longer than 50 characters (after stripping HTML tags).\n * @param {Paper} paper The paper to analyze.\n * @returns {Node[]} An array of nodes containing too long center-aligned paragraphs/headings.\n */\nexport default function( paper ) {\n\tconst tree = paper.getTree();\n\n\tconst paragraphs = tree.findAll( node => node.name === \"p\" );\n\tconst headings = tree.findAll( node => HEADING_TAGS_REGEX.test( node.name ) );\n\n\treturn getLongCenterAlignedElements( paragraphs.concat( headings ) );\n}\n"],"mappings":";;;;;;AAAA;AACA;AACA;AACA;AACA,MAAMA,yBAAyB,GAAG,EAAE;;AAEpC;AACA;AACA;AACA;AACA,MAAMC,kBAAkB,GAAG,UAAU;;AAErC;AACA;AACA;AACA;AACA;AACA,SAASC,4BAA4BA,CAAEC,KAAK,EAAG;EAC9C,OAAOA,KAAK,CAACC,MAAM,CAAEC,IAAI,IAAI;IAC5B,MAAMC,eAAe,GAAGD,IAAI,CAACE,UAAU,CAACC,KAAK,YAAYC,GAAG,IAAIJ,IAAI,CAACE,UAAU,CAACC,KAAK,CAACE,GAAG,CAAE,uBAAwB,CAAC;IACpH,OAAOJ,eAAe,IAAID,IAAI,CAACM,SAAS,CAAC,CAAC,CAACC,MAAM,GAAGZ,yBAAyB;EAC9E,CAAE,CAAC;AACJ;;AAEA;AACA;AACA;AACA;AACA;AACe,SAAAa,SAAUC,KAAK,EAAG;EAChC,MAAMC,IAAI,GAAGD,KAAK,CAACE,OAAO,CAAC,CAAC;EAE5B,MAAMC,UAAU,GAAGF,IAAI,CAACG,OAAO,CAAEb,IAAI,IAAIA,IAAI,CAACc,IAAI,KAAK,GAAI,CAAC;EAC5D,MAAMC,QAAQ,GAAGL,IAAI,CAACG,OAAO,CAAEb,IAAI,IAAIJ,kBAAkB,CAACoB,IAAI,CAAEhB,IAAI,CAACc,IAAK,CAAE,CAAC;EAE7E,OAAOjB,4BAA4B,CAAEe,UAAU,CAACK,MAAM,CAAEF,QAAS,CAAE,CAAC;AACrE","ignoreList":[]}

package/build/cjs/languageProcessing/researches/getParagraphLength.js

@@ -0,0 +1,49 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = _default;
+var _imageInText = require("../helpers/image/imageInText");
+var _sanitizeLineBreakTag = _interopRequireDefault(require("../helpers/sanitize/sanitizeLineBreakTag"));
+var _countWords = _interopRequireDefault(require("../helpers/word/countWords.js"));
+var _matchParagraphs = _interopRequireDefault(require("../helpers/html/matchParagraphs.js"));
+var _lodash = require("lodash");
+var _htmlParser = _interopRequireDefault(require("../helpers/html/htmlParser"));
+var _helpers = require("../helpers");
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+/**
+ * Gets all paragraphs and their word counts or character counts from the text.
+ *
+ * @param {Paper} 		paper 		The paper object to get the text from.
+ * @param {Researcher} 	researcher 	The researcher to use for analysis.
+ *
+ * @returns {Array} The array containing an object with the paragraph word or character count and paragraph text.
+ */
+function _default(paper, researcher) {
+  let text = paper.getText();
+  text = (0, _htmlParser.default)(text);
+  text = (0, _helpers.filterShortcodesFromHTML)(text, paper._attributes && paper._attributes.shortcodes);
+
+  // Remove images from text before retrieving the paragraphs.
+  // This step is done here so that applying highlight in captions is possible for ParagraphTooLongAssessment.
+  text = text.replace(_imageInText.imageRegex, "");
+
+  // Replace line break tags containing attribute(s) with paragraph tag.
+  text = (0, _sanitizeLineBreakTag.default)(text);
+  const paragraphs = (0, _matchParagraphs.default)(text);
+  const paragraphsLength = [];
+
+  // An optional custom helper to count length to use instead of countWords.
+  const customCountLength = researcher.getHelper("customCountLength");
+  paragraphs.map(function (paragraph) {
+    paragraphsLength.push({
+      countLength: customCountLength ? customCountLength(paragraph) : (0, _countWords.default)(paragraph),
+      text: paragraph
+    });
+  });
+  return (0, _lodash.filter)(paragraphsLength, function (paragraphLength) {
+    return paragraphLength.countLength > 0;
+  });
+}
+//# sourceMappingURL=getParagraphLength.js.map

package/build/cjs/languageProcessing/researches/getParagraphLength.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"getParagraphLength.js","names":["_imageInText","require","_sanitizeLineBreakTag","_interopRequireDefault","_countWords","_matchParagraphs","_lodash","_htmlParser","_helpers","e","__esModule","default","_default","paper","researcher","text","getText","removeHtmlBlocks","filterShortcodesFromHTML","_attributes","shortcodes","replace","imageRegex","sanitizeLineBreakTag","paragraphs","matchParagraphs","paragraphsLength","customCountLength","getHelper","map","paragraph","push","countLength","countWords","filter","paragraphLength"],"sources":["../../../../src/languageProcessing/researches/getParagraphLength.js"],"sourcesContent":["import { imageRegex } from \"../helpers/image/imageInText\";\nimport sanitizeLineBreakTag from \"../helpers/sanitize/sanitizeLineBreakTag\";\nimport countWords from \"../helpers/word/countWords.js\";\nimport matchParagraphs from \"../helpers/html/matchParagraphs.js\";\nimport { filter } from \"lodash\";\nimport removeHtmlBlocks from \"../helpers/html/htmlParser\";\nimport { filterShortcodesFromHTML } from \"../helpers\";\n\n/**\n * Gets all paragraphs and their word counts or character counts from the text.\n *\n * @param {Paper} \t\tpaper \t\tThe paper object to get the text from.\n * @param {Researcher} \tresearcher \tThe researcher to use for analysis.\n *\n * @returns {Array} The array containing an object with the paragraph word or character count and paragraph text.\n */\nexport default function( paper, researcher ) {\n\tlet text = paper.getText();\n\ttext = removeHtmlBlocks( text );\n\ttext = filterShortcodesFromHTML( text, paper._attributes && paper._attributes.shortcodes );\n\n\t// Remove images from text before retrieving the paragraphs.\n\t// This step is done here so that applying highlight in captions is possible for ParagraphTooLongAssessment.\n\ttext = text.replace( imageRegex, \"\" );\n\n\t// Replace line break tags containing attribute(s) with paragraph tag.\n\ttext = sanitizeLineBreakTag( text );\n\tconst paragraphs = matchParagraphs( text );\n\tconst paragraphsLength = [];\n\n\t// An optional custom helper to count length to use instead of countWords.\n\tconst customCountLength = researcher.getHelper( \"customCountLength\" );\n\n\tparagraphs.map( function( paragraph ) {\n\t\tparagraphsLength.push( {\n\t\t\tcountLength: customCountLength ? customCountLength( paragraph ) : countWords( paragraph ),\n\t\t\ttext: paragraph,\n\t\t} );\n\t} );\n\n\treturn filter( paragraphsLength, function( paragraphLength ) {\n\t\treturn ( paragraphLength.countLength > 0 );\n\t} );\n}\n"],"mappings":";;;;;;AAAA,IAAAA,YAAA,GAAAC,OAAA;AACA,IAAAC,qBAAA,GAAAC,sBAAA,CAAAF,OAAA;AACA,IAAAG,WAAA,GAAAD,sBAAA,CAAAF,OAAA;AACA,IAAAI,gBAAA,GAAAF,sBAAA,CAAAF,OAAA;AACA,IAAAK,OAAA,GAAAL,OAAA;AACA,IAAAM,WAAA,GAAAJ,sBAAA,CAAAF,OAAA;AACA,IAAAO,QAAA,GAAAP,OAAA;AAAsD,SAAAE,uBAAAM,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAEtD;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAAAG,SAAUC,KAAK,EAAEC,UAAU,EAAG;EAC5C,IAAIC,IAAI,GAAGF,KAAK,CAACG,OAAO,CAAC,CAAC;EAC1BD,IAAI,GAAG,IAAAE,mBAAgB,EAAEF,IAAK,CAAC;EAC/BA,IAAI,GAAG,IAAAG,iCAAwB,EAAEH,IAAI,EAAEF,KAAK,CAACM,WAAW,IAAIN,KAAK,CAACM,WAAW,CAACC,UAAW,CAAC;;EAE1F;EACA;EACAL,IAAI,GAAGA,IAAI,CAACM,OAAO,CAAEC,uBAAU,EAAE,EAAG,CAAC;;EAErC;EACAP,IAAI,GAAG,IAAAQ,6BAAoB,EAAER,IAAK,CAAC;EACnC,MAAMS,UAAU,GAAG,IAAAC,wBAAe,EAAEV,IAAK,CAAC;EAC1C,MAAMW,gBAAgB,GAAG,EAAE;;EAE3B;EACA,MAAMC,iBAAiB,GAAGb,UAAU,CAACc,SAAS,CAAE,mBAAoB,CAAC;EAErEJ,UAAU,CAACK,GAAG,CAAE,UAAUC,SAAS,EAAG;IACrCJ,gBAAgB,CAACK,IAAI,CAAE;MACtBC,WAAW,EAAEL,iBAAiB,GAAGA,iBAAiB,CAAEG,SAAU,CAAC,GAAG,IAAAG,mBAAU,EAAEH,SAAU,CAAC;MACzFf,IAAI,EAAEe;IACP,CAAE,CAAC;EACJ,CAAE,CAAC;EAEH,OAAO,IAAAI,cAAM,EAAER,gBAAgB,EAAE,UAAUS,eAAe,EAAG;IAC5D,OAASA,eAAe,CAACH,WAAW,GAAG,CAAC;EACzC,CAAE,CAAC;AACJ","ignoreList":[]}

package/build/cjs/languageProcessing/researches/getParagraphs.js

@@ -0,0 +1,32 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = _default;
+var _lodash = require("lodash");
+/**
+ * Returns all paragraphs in a given Paper.
+ * Remove paragraphs that do not contain sentences or only consist of links.
+ *
+ * @param {Paper} paper The current paper.
+ * @returns {Paragraph[]} All paragraphs in the paper.
+ */
+function _default(paper) {
+  let paragraphs = paper.getTree().findAll(node => node.name === 'p');
+
+  // Remove empty paragraphs without sentences and paragraphs only consisting of empty links.
+  paragraphs = (0, _lodash.reject)(paragraphs, paragraph => paragraph.sentences.length === 0);
+  // Don't remove paragraphs with links that contain meaningful text
+  paragraphs = (0, _lodash.reject)(paragraphs, paragraph => {
+    // Only reject if ALL children are links AND those links are empty/meaningless
+    const allLinks = paragraph.childNodes.every(node => node.name === 'a');
+    if (!allLinks) return false;
+
+    // Check if the paragraph has meaningful text content
+    const textContent = paragraph.innerText().trim();
+    return textContent.length === 0; // Only reject if completely empty
+  });
+  return paragraphs;
+}
+//# sourceMappingURL=getParagraphs.js.map

package/build/cjs/languageProcessing/researches/getParagraphs.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"getParagraphs.js","names":["_lodash","require","_default","paper","paragraphs","getTree","findAll","node","name","reject","paragraph","sentences","length","allLinks","childNodes","every","textContent","innerText","trim"],"sources":["../../../../src/languageProcessing/researches/getParagraphs.js"],"sourcesContent":["import {reject} from 'lodash';\n\n/**\n * Returns all paragraphs in a given Paper.\n * Remove paragraphs that do not contain sentences or only consist of links.\n *\n * @param {Paper} paper The current paper.\n * @returns {Paragraph[]} All paragraphs in the paper.\n */\nexport default function(paper) {\n  let paragraphs = paper.getTree().findAll(node => node.name === 'p');\n\n  // Remove empty paragraphs without sentences and paragraphs only consisting of empty links.\n  paragraphs = reject(paragraphs, paragraph => paragraph.sentences.length === 0);\n  // Don't remove paragraphs with links that contain meaningful text\n  paragraphs = reject(paragraphs, paragraph => {\n    // Only reject if ALL children are links AND those links are empty/meaningless\n    const allLinks = paragraph.childNodes.every(node => node.name === 'a');\n    if (!allLinks) return false;\n\n    // Check if the paragraph has meaningful text content\n    const textContent = paragraph.innerText().trim();\n    return textContent.length === 0; // Only reject if completely empty\n  });\n\n  return paragraphs;\n}\n"],"mappings":";;;;;;AAAA,IAAAA,OAAA,GAAAC,OAAA;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAAAC,SAASC,KAAK,EAAE;EAC7B,IAAIC,UAAU,GAAGD,KAAK,CAACE,OAAO,CAAC,CAAC,CAACC,OAAO,CAACC,IAAI,IAAIA,IAAI,CAACC,IAAI,KAAK,GAAG,CAAC;;EAEnE;EACAJ,UAAU,GAAG,IAAAK,cAAM,EAACL,UAAU,EAAEM,SAAS,IAAIA,SAAS,CAACC,SAAS,CAACC,MAAM,KAAK,CAAC,CAAC;EAC9E;EACAR,UAAU,GAAG,IAAAK,cAAM,EAACL,UAAU,EAAEM,SAAS,IAAI;IAC3C;IACA,MAAMG,QAAQ,GAAGH,SAAS,CAACI,UAAU,CAACC,KAAK,CAACR,IAAI,IAAIA,IAAI,CAACC,IAAI,KAAK,GAAG,CAAC;IACtE,IAAI,CAACK,QAAQ,EAAE,OAAO,KAAK;;IAE3B;IACA,MAAMG,WAAW,GAAGN,SAAS,CAACO,SAAS,CAAC,CAAC,CAACC,IAAI,CAAC,CAAC;IAChD,OAAOF,WAAW,CAACJ,MAAM,KAAK,CAAC,CAAC,CAAC;EACnC,CAAC,CAAC;EAEF,OAAOR,UAAU;AACnB","ignoreList":[]}

package/build/cjs/languageProcessing/researches/getPassiveVoiceResult.js

@@ -0,0 +1,127 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = getPassiveVoice;
+exports.getPeriphrasticPassives = exports.getMorphologicalPassives = void 0;
+var _getSentences = _interopRequireDefault(require("../helpers/sentence/getSentences.js"));
+var _stripHTMLTags = require("../helpers/sanitize/stripHTMLTags.js");
+var _Sentence = _interopRequireDefault(require("../../languageProcessing/values/Sentence.js"));
+var _lodash = require("lodash");
+var _htmlParser = _interopRequireDefault(require("../helpers/html/htmlParser"));
+var _helpers = require("../helpers");
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+/**
+ * Looks for morphological passive voice.
+ * Supported morphological languages: "ru", "sv", "id", "ar", "he", "tr", "fa".
+ * Farsi is implemented as morphological because the periphrastic passives are used as compound verbs (among other compound passives).
+ * @param {Paper}      paper      The paper object.
+ * @param {Researcher} researcher The researcher.
+ *
+ * @returns {Object} The found passive sentences.
+ */
+const getMorphologicalPassives = function (paper, researcher) {
+  const isPassiveSentence = researcher.getHelper("isPassiveSentence");
+  let text = paper.getText();
+  text = (0, _htmlParser.default)(text);
+  text = (0, _helpers.filterShortcodesFromHTML)(text, paper._attributes && paper._attributes.shortcodes);
+  const memoizedTokenizer = researcher.getHelper("memoizedTokenizer");
+  const sentences = (0, _getSentences.default)(text, memoizedTokenizer).map(function (sentence) {
+    return new _Sentence.default(sentence);
+  });
+  const totalNumberSentences = sentences.length;
+  const passiveSentences = [];
+  (0, _lodash.forEach)(sentences, function (sentence) {
+    const strippedSentence = (0, _stripHTMLTags.stripFullTags)(sentence.getSentenceText()).toLocaleLowerCase();
+    sentence.setPassive(isPassiveSentence(strippedSentence));
+    if (sentence.isPassive() === true) {
+      passiveSentences.push(sentence.getSentenceText());
+    }
+  });
+  return {
+    total: totalNumberSentences,
+    passives: passiveSentences
+  };
+};
+
+/**
+ * Looks for periphrastic passive voice.
+ * Supported periphrastic languages: "en", "de", "nl", "fr", "es", "it", "pt", "pl", "sk".
+ *
+ * @param {Paper}      paper      The paper object.
+ * @param {Researcher} researcher The researcher.
+ *
+ * @returns {Object} The found passive sentences.
+ */
+exports.getMorphologicalPassives = getMorphologicalPassives;
+const getPeriphrasticPassives = function (paper, researcher) {
+  const getClauses = researcher.getHelper("getClauses");
+  let text = paper.getText();
+  text = (0, _htmlParser.default)(text);
+  text = (0, _helpers.filterShortcodesFromHTML)(text, paper._attributes && paper._attributes.shortcodes);
+  const memoizedTokenizer = researcher.getHelper("memoizedTokenizer");
+  const sentences = (0, _getSentences.default)(text, memoizedTokenizer).map(function (sentence) {
+    return new _Sentence.default(sentence);
+  });
+  const totalNumberSentences = sentences.length;
+  const passiveSentences = [];
+  (0, _lodash.forEach)(sentences, function (sentence) {
+    const strippedSentence = (0, _stripHTMLTags.stripFullTags)(sentence.getSentenceText()).toLocaleLowerCase();
+
+    // The functionality based on sentencePart objects should be rewritten using array indices of stopwords and auxiliaries.
+
+    // Divide a sentence into clauses and return an array of clause objects that have been checked for passiveness.
+    const clauses = getClauses(strippedSentence);
+    sentence.setClauses(clauses);
+
+    // Check sentence passiveness based on its clause passiveness.
+    if (sentence.isPassive()) {
+      passiveSentences.push(sentence.getSentenceText());
+    }
+  });
+  return {
+    total: totalNumberSentences,
+    passives: passiveSentences
+  };
+};
+
+/**
+ * Looks for both morphological and periphrastic passive voice
+ * Supported languages with both morphological and periphrastic passives: "hu", "nb".
+ * Due to technical difficulties "nb" is only implemented as periphrastic at the moment. Languages that have not been implemented yet: "da".
+ *
+ * @param {Paper}      paper      The paper object.
+ * @param {Researcher} researcher The researcher.
+ *
+ * @returns {Object} The found passive sentences.
+ */
+exports.getPeriphrasticPassives = getPeriphrasticPassives;
+const getMorphologicalAndPeriphrasticPassive = function (paper, researcher) {
+  const morphologicalPassives = getMorphologicalPassives(paper, researcher);
+  const periphrasticPassives = getPeriphrasticPassives(paper, researcher).passives;
+  return {
+    total: morphologicalPassives.total,
+    passives: periphrasticPassives.concat(morphologicalPassives.passives)
+  };
+};
+
+/**
+ * Looks for passive voice.
+ *
+ * @param {Paper}      paper      The paper object.
+ * @param {Researcher} researcher The researcher.
+ *
+ * @returns {Object} The found passive sentences.
+ */
+function getPassiveVoice(paper, researcher) {
+  const passiveType = researcher.getConfig("passiveConstructionType");
+  if (passiveType === "periphrastic") {
+    return getPeriphrasticPassives(paper, researcher);
+  }
+  if (passiveType === "morphological") {
+    return getMorphologicalPassives(paper, researcher);
+  }
+  return getMorphologicalAndPeriphrasticPassive(paper, researcher);
+}
+//# sourceMappingURL=getPassiveVoiceResult.js.map

package/build/cjs/languageProcessing/researches/getPassiveVoiceResult.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"getPassiveVoiceResult.js","names":["_getSentences","_interopRequireDefault","require","_stripHTMLTags","_Sentence","_lodash","_htmlParser","_helpers","e","__esModule","default","getMorphologicalPassives","paper","researcher","isPassiveSentence","getHelper","text","getText","removeHtmlBlocks","filterShortcodesFromHTML","_attributes","shortcodes","memoizedTokenizer","sentences","getSentences","map","sentence","Sentence","totalNumberSentences","length","passiveSentences","forEach","strippedSentence","stripHTMLTags","getSentenceText","toLocaleLowerCase","setPassive","isPassive","push","total","passives","exports","getPeriphrasticPassives","getClauses","clauses","setClauses","getMorphologicalAndPeriphrasticPassive","morphologicalPassives","periphrasticPassives","concat","getPassiveVoice","passiveType","getConfig"],"sources":["../../../../src/languageProcessing/researches/getPassiveVoiceResult.js"],"sourcesContent":["import getSentences from \"../helpers/sentence/getSentences.js\";\nimport { stripFullTags as stripHTMLTags } from \"../helpers/sanitize/stripHTMLTags.js\";\nimport Sentence from \"../../languageProcessing/values/Sentence.js\";\n\nimport { forEach } from \"lodash\";\nimport removeHtmlBlocks from \"../helpers/html/htmlParser\";\nimport { filterShortcodesFromHTML } from \"../helpers\";\n\n/**\n * Looks for morphological passive voice.\n * Supported morphological languages: \"ru\", \"sv\", \"id\", \"ar\", \"he\", \"tr\", \"fa\".\n * Farsi is implemented as morphological because the periphrastic passives are used as compound verbs (among other compound passives).\n * @param {Paper}      paper      The paper object.\n * @param {Researcher} researcher The researcher.\n *\n * @returns {Object} The found passive sentences.\n */\nexport const getMorphologicalPassives = function( paper, researcher ) {\n\tconst isPassiveSentence = researcher.getHelper( \"isPassiveSentence\" );\n\tlet text = paper.getText();\n\ttext = removeHtmlBlocks( text );\n\ttext = filterShortcodesFromHTML( text, paper._attributes && paper._attributes.shortcodes );\n\tconst memoizedTokenizer = researcher.getHelper( \"memoizedTokenizer\" );\n\tconst sentences = getSentences( text, memoizedTokenizer )\n\t\t.map( function( sentence ) {\n\t\t\treturn new Sentence( sentence );\n\t\t} );\n\tconst totalNumberSentences = sentences.length;\n\tconst passiveSentences = [];\n\n\tforEach( sentences, function( sentence ) {\n\t\tconst strippedSentence = stripHTMLTags( sentence.getSentenceText() ).toLocaleLowerCase();\n\n\t\tsentence.setPassive( isPassiveSentence( strippedSentence ) );\n\n\t\tif ( sentence.isPassive() === true ) {\n\t\t\tpassiveSentences.push( sentence.getSentenceText() );\n\t\t}\n\t} );\n\n\treturn {\n\t\ttotal: totalNumberSentences,\n\t\tpassives: passiveSentences,\n\t};\n};\n\n/**\n * Looks for periphrastic passive voice.\n * Supported periphrastic languages: \"en\", \"de\", \"nl\", \"fr\", \"es\", \"it\", \"pt\", \"pl\", \"sk\".\n *\n * @param {Paper}      paper      The paper object.\n * @param {Researcher} researcher The researcher.\n *\n * @returns {Object} The found passive sentences.\n */\nexport const getPeriphrasticPassives = function( paper, researcher ) {\n\tconst getClauses = researcher.getHelper( \"getClauses\" );\n\tlet text = paper.getText();\n\ttext = removeHtmlBlocks( text );\n\ttext = filterShortcodesFromHTML( text, paper._attributes && paper._attributes.shortcodes );\n\tconst memoizedTokenizer = researcher.getHelper( \"memoizedTokenizer\" );\n\tconst sentences = getSentences( text, memoizedTokenizer )\n\t\t.map( function( sentence ) {\n\t\t\treturn new Sentence( sentence );\n\t\t} );\n\tconst totalNumberSentences = sentences.length;\n\tconst passiveSentences = [];\n\n\tforEach( sentences, function( sentence ) {\n\t\tconst strippedSentence = stripHTMLTags( sentence.getSentenceText() ).toLocaleLowerCase();\n\n\t\t// The functionality based on sentencePart objects should be rewritten using array indices of stopwords and auxiliaries.\n\n\t\t// Divide a sentence into clauses and return an array of clause objects that have been checked for passiveness.\n\t\tconst clauses = getClauses( strippedSentence );\n\t\tsentence.setClauses( clauses );\n\n\t\t// Check sentence passiveness based on its clause passiveness.\n\t\tif ( sentence.isPassive() ) {\n\t\t\tpassiveSentences.push( sentence.getSentenceText() );\n\t\t}\n\t} );\n\n\treturn {\n\t\ttotal: totalNumberSentences,\n\t\tpassives: passiveSentences,\n\t};\n};\n\n/**\n * Looks for both morphological and periphrastic passive voice\n * Supported languages with both morphological and periphrastic passives: \"hu\", \"nb\".\n * Due to technical difficulties \"nb\" is only implemented as periphrastic at the moment. Languages that have not been implemented yet: \"da\".\n *\n * @param {Paper}      paper      The paper object.\n * @param {Researcher} researcher The researcher.\n *\n * @returns {Object} The found passive sentences.\n */\nconst getMorphologicalAndPeriphrasticPassive = function( paper, researcher ) {\n\tconst morphologicalPassives = getMorphologicalPassives( paper, researcher );\n\tconst periphrasticPassives = getPeriphrasticPassives( paper, researcher ).passives;\n\n\treturn {\n\t\ttotal: morphologicalPassives.total,\n\t\tpassives: periphrasticPassives.concat( morphologicalPassives.passives ),\n\t};\n};\n\n/**\n * Looks for passive voice.\n *\n * @param {Paper}      paper      The paper object.\n * @param {Researcher} researcher The researcher.\n *\n * @returns {Object} The found passive sentences.\n */\nexport default function getPassiveVoice( paper, researcher ) {\n\tconst passiveType = researcher.getConfig( \"passiveConstructionType\" );\n\n\tif ( passiveType === \"periphrastic\" ) {\n\t\treturn getPeriphrasticPassives( paper, researcher );\n\t}\n\tif ( passiveType === \"morphological\" ) {\n\t\treturn getMorphologicalPassives( paper, researcher );\n\t}\n\n\treturn getMorphologicalAndPeriphrasticPassive( paper, researcher );\n}\n"],"mappings":";;;;;;;AAAA,IAAAA,aAAA,GAAAC,sBAAA,CAAAC,OAAA;AACA,IAAAC,cAAA,GAAAD,OAAA;AACA,IAAAE,SAAA,GAAAH,sBAAA,CAAAC,OAAA;AAEA,IAAAG,OAAA,GAAAH,OAAA;AACA,IAAAI,WAAA,GAAAL,sBAAA,CAAAC,OAAA;AACA,IAAAK,QAAA,GAAAL,OAAA;AAAsD,SAAAD,uBAAAO,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAEtD;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACO,MAAMG,wBAAwB,GAAG,SAAAA,CAAUC,KAAK,EAAEC,UAAU,EAAG;EACrE,MAAMC,iBAAiB,GAAGD,UAAU,CAACE,SAAS,CAAE,mBAAoB,CAAC;EACrE,IAAIC,IAAI,GAAGJ,KAAK,CAACK,OAAO,CAAC,CAAC;EAC1BD,IAAI,GAAG,IAAAE,mBAAgB,EAAEF,IAAK,CAAC;EAC/BA,IAAI,GAAG,IAAAG,iCAAwB,EAAEH,IAAI,EAAEJ,KAAK,CAACQ,WAAW,IAAIR,KAAK,CAACQ,WAAW,CAACC,UAAW,CAAC;EAC1F,MAAMC,iBAAiB,GAAGT,UAAU,CAACE,SAAS,CAAE,mBAAoB,CAAC;EACrE,MAAMQ,SAAS,GAAG,IAAAC,qBAAY,EAAER,IAAI,EAAEM,iBAAkB,CAAC,CACvDG,GAAG,CAAE,UAAUC,QAAQ,EAAG;IAC1B,OAAO,IAAIC,iBAAQ,CAAED,QAAS,CAAC;EAChC,CAAE,CAAC;EACJ,MAAME,oBAAoB,GAAGL,SAAS,CAACM,MAAM;EAC7C,MAAMC,gBAAgB,GAAG,EAAE;EAE3B,IAAAC,eAAO,EAAER,SAAS,EAAE,UAAUG,QAAQ,EAAG;IACxC,MAAMM,gBAAgB,GAAG,IAAAC,4BAAa,EAAEP,QAAQ,CAACQ,eAAe,CAAC,CAAE,CAAC,CAACC,iBAAiB,CAAC,CAAC;IAExFT,QAAQ,CAACU,UAAU,CAAEtB,iBAAiB,CAAEkB,gBAAiB,CAAE,CAAC;IAE5D,IAAKN,QAAQ,CAACW,SAAS,CAAC,CAAC,KAAK,IAAI,EAAG;MACpCP,gBAAgB,CAACQ,IAAI,CAAEZ,QAAQ,CAACQ,eAAe,CAAC,CAAE,CAAC;IACpD;EACD,CAAE,CAAC;EAEH,OAAO;IACNK,KAAK,EAAEX,oBAAoB;IAC3BY,QAAQ,EAAEV;EACX,CAAC;AACF,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AARAW,OAAA,CAAA9B,wBAAA,GAAAA,wBAAA;AASO,MAAM+B,uBAAuB,GAAG,SAAAA,CAAU9B,KAAK,EAAEC,UAAU,EAAG;EACpE,MAAM8B,UAAU,GAAG9B,UAAU,CAACE,SAAS,CAAE,YAAa,CAAC;EACvD,IAAIC,IAAI,GAAGJ,KAAK,CAACK,OAAO,CAAC,CAAC;EAC1BD,IAAI,GAAG,IAAAE,mBAAgB,EAAEF,IAAK,CAAC;EAC/BA,IAAI,GAAG,IAAAG,iCAAwB,EAAEH,IAAI,EAAEJ,KAAK,CAACQ,WAAW,IAAIR,KAAK,CAACQ,WAAW,CAACC,UAAW,CAAC;EAC1F,MAAMC,iBAAiB,GAAGT,UAAU,CAACE,SAAS,CAAE,mBAAoB,CAAC;EACrE,MAAMQ,SAAS,GAAG,IAAAC,qBAAY,EAAER,IAAI,EAAEM,iBAAkB,CAAC,CACvDG,GAAG,CAAE,UAAUC,QAAQ,EAAG;IAC1B,OAAO,IAAIC,iBAAQ,CAAED,QAAS,CAAC;EAChC,CAAE,CAAC;EACJ,MAAME,oBAAoB,GAAGL,SAAS,CAACM,MAAM;EAC7C,MAAMC,gBAAgB,GAAG,EAAE;EAE3B,IAAAC,eAAO,EAAER,SAAS,EAAE,UAAUG,QAAQ,EAAG;IACxC,MAAMM,gBAAgB,GAAG,IAAAC,4BAAa,EAAEP,QAAQ,CAACQ,eAAe,CAAC,CAAE,CAAC,CAACC,iBAAiB,CAAC,CAAC;;IAExF;;IAEA;IACA,MAAMS,OAAO,GAAGD,UAAU,CAAEX,gBAAiB,CAAC;IAC9CN,QAAQ,CAACmB,UAAU,CAAED,OAAQ,CAAC;;IAE9B;IACA,IAAKlB,QAAQ,CAACW,SAAS,CAAC,CAAC,EAAG;MAC3BP,gBAAgB,CAACQ,IAAI,CAAEZ,QAAQ,CAACQ,eAAe,CAAC,CAAE,CAAC;IACpD;EACD,CAAE,CAAC;EAEH,OAAO;IACNK,KAAK,EAAEX,oBAAoB;IAC3BY,QAAQ,EAAEV;EACX,CAAC;AACF,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AATAW,OAAA,CAAAC,uBAAA,GAAAA,uBAAA;AAUA,MAAMI,sCAAsC,GAAG,SAAAA,CAAUlC,KAAK,EAAEC,UAAU,EAAG;EAC5E,MAAMkC,qBAAqB,GAAGpC,wBAAwB,CAAEC,KAAK,EAAEC,UAAW,CAAC;EAC3E,MAAMmC,oBAAoB,GAAGN,uBAAuB,CAAE9B,KAAK,EAAEC,UAAW,CAAC,CAAC2B,QAAQ;EAElF,OAAO;IACND,KAAK,EAAEQ,qBAAqB,CAACR,KAAK;IAClCC,QAAQ,EAAEQ,oBAAoB,CAACC,MAAM,CAAEF,qBAAqB,CAACP,QAAS;EACvE,CAAC;AACF,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAASU,eAAeA,CAAEtC,KAAK,EAAEC,UAAU,EAAG;EAC5D,MAAMsC,WAAW,GAAGtC,UAAU,CAACuC,SAAS,CAAE,yBAA0B,CAAC;EAErE,IAAKD,WAAW,KAAK,cAAc,EAAG;IACrC,OAAOT,uBAAuB,CAAE9B,KAAK,EAAEC,UAAW,CAAC;EACpD;EACA,IAAKsC,WAAW,KAAK,eAAe,EAAG;IACtC,OAAOxC,wBAAwB,CAAEC,KAAK,EAAEC,UAAW,CAAC;EACrD;EAEA,OAAOiC,sCAAsC,CAAElC,KAAK,EAAEC,UAAW,CAAC;AACnE","ignoreList":[]}

package/build/cjs/languageProcessing/researches/getProminentWordsForInsights.js

@@ -0,0 +1,45 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = void 0;
+var _lodash = require("lodash");
+var _determineProminentWords = require("../helpers/prominentWords/determineProminentWords");
+var _removeURLs = _interopRequireDefault(require("../helpers/sanitize/removeURLs.js"));
+var _removeEmailAddresses = _interopRequireDefault(require("../helpers/sanitize/removeEmailAddresses"));
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+/**
+ * Retrieves the prominent words from the given paper.
+ *
+ * @param {Paper} paper             The paper to determine the prominent words of.
+ * @param {Researcher} researcher   The researcher to use for analysis.
+ *
+ * @returns {WordCombination[]} Prominent words for this paper, filtered and sorted.
+ */
+function getProminentWordsForInsights(paper, researcher) {
+  const functionWords = researcher.getConfig("functionWords");
+  // An optional custom helper to return custom function to return the stem of a word.
+  const customStemmer = researcher.getHelper("customGetStemmer");
+  const stemmer = customStemmer ? customStemmer(researcher) : researcher.getHelper("getStemmer")(researcher);
+  // An optional custom helper to get words from the text.
+  const getWordsCustomHelper = researcher.getHelper("getWordsCustomHelper");
+  let text = paper.getText();
+  // We don't want to include URLs or email addresses in prominent words.
+  text = (0, _removeURLs.default)(text);
+  text = (0, _removeEmailAddresses.default)(text);
+
+  // If the language has a custom helper to get words from the text, we don't retrieve the abbreviation.
+  const abbreviations = getWordsCustomHelper ? [] : (0, _determineProminentWords.retrieveAbbreviations)(text);
+  const prominentWordsFromText = (0, _determineProminentWords.getProminentWords)(text, abbreviations, stemmer, functionWords, getWordsCustomHelper);
+  const collapsedWords = (0, _determineProminentWords.collapseProminentWordsOnStem)(prominentWordsFromText);
+  (0, _determineProminentWords.sortProminentWords)(collapsedWords);
+
+  /*
+   * Collapse the list of prominent words on stems, sort it, filter out all words that occur less than
+   * 5 times in the text. Return the 20 top items from this list.
+   */
+  return (0, _lodash.take)((0, _determineProminentWords.filterProminentWords)(collapsedWords, 5), 20);
+}
+var _default = exports.default = getProminentWordsForInsights;
+//# sourceMappingURL=getProminentWordsForInsights.js.map

package/build/cjs/languageProcessing/researches/getProminentWordsForInsights.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"getProminentWordsForInsights.js","names":["_lodash","require","_determineProminentWords","_removeURLs","_interopRequireDefault","_removeEmailAddresses","e","__esModule","default","getProminentWordsForInsights","paper","researcher","functionWords","getConfig","customStemmer","getHelper","stemmer","getWordsCustomHelper","text","getText","removeURLs","removeEmailAddresses","abbreviations","retrieveAbbreviations","prominentWordsFromText","getProminentWords","collapsedWords","collapseProminentWordsOnStem","sortProminentWords","take","filterProminentWords","_default","exports"],"sources":["../../../../src/languageProcessing/researches/getProminentWordsForInsights.js"],"sourcesContent":["import { take } from \"lodash\";\nimport {\n\tcollapseProminentWordsOnStem,\n\tfilterProminentWords,\n\tgetProminentWords,\n\tretrieveAbbreviations,\n\tsortProminentWords,\n} from \"../helpers/prominentWords/determineProminentWords\";\nimport removeURLs from \"../helpers/sanitize/removeURLs.js\";\nimport removeEmailAddresses from \"../helpers/sanitize/removeEmailAddresses\";\n\n/**\n * Retrieves the prominent words from the given paper.\n *\n * @param {Paper} paper             The paper to determine the prominent words of.\n * @param {Researcher} researcher   The researcher to use for analysis.\n *\n * @returns {WordCombination[]} Prominent words for this paper, filtered and sorted.\n */\nfunction getProminentWordsForInsights( paper, researcher ) {\n\tconst functionWords = researcher.getConfig( \"functionWords\" );\n\t// An optional custom helper to return custom function to return the stem of a word.\n\tconst customStemmer = researcher.getHelper( \"customGetStemmer\" );\n\tconst stemmer = customStemmer ? customStemmer( researcher ) : researcher.getHelper( \"getStemmer\" )( researcher );\n\t// An optional custom helper to get words from the text.\n\tconst getWordsCustomHelper = researcher.getHelper( \"getWordsCustomHelper\" );\n\n\tlet text = paper.getText();\n\t// We don't want to include URLs or email addresses in prominent words.\n\ttext = removeURLs( text );\n\ttext = removeEmailAddresses( text );\n\n\t// If the language has a custom helper to get words from the text, we don't retrieve the abbreviation.\n\tconst abbreviations = getWordsCustomHelper ? [] : retrieveAbbreviations( text );\n\n\tconst prominentWordsFromText = getProminentWords( text, abbreviations, stemmer, functionWords, getWordsCustomHelper );\n\n\tconst collapsedWords = collapseProminentWordsOnStem( prominentWordsFromText );\n\tsortProminentWords( collapsedWords );\n\n\t/*\n\t * Collapse the list of prominent words on stems, sort it, filter out all words that occur less than\n\t * 5 times in the text. Return the 20 top items from this list.\n\t */\n\treturn take( filterProminentWords( collapsedWords, 5 ), 20 );\n}\n\nexport default getProminentWordsForInsights;\n"],"mappings":";;;;;;AAAA,IAAAA,OAAA,GAAAC,OAAA;AACA,IAAAC,wBAAA,GAAAD,OAAA;AAOA,IAAAE,WAAA,GAAAC,sBAAA,CAAAH,OAAA;AACA,IAAAI,qBAAA,GAAAD,sBAAA,CAAAH,OAAA;AAA4E,SAAAG,uBAAAE,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAE5E;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASG,4BAA4BA,CAAEC,KAAK,EAAEC,UAAU,EAAG;EAC1D,MAAMC,aAAa,GAAGD,UAAU,CAACE,SAAS,CAAE,eAAgB,CAAC;EAC7D;EACA,MAAMC,aAAa,GAAGH,UAAU,CAACI,SAAS,CAAE,kBAAmB,CAAC;EAChE,MAAMC,OAAO,GAAGF,aAAa,GAAGA,aAAa,CAAEH,UAAW,CAAC,GAAGA,UAAU,CAACI,SAAS,CAAE,YAAa,CAAC,CAAEJ,UAAW,CAAC;EAChH;EACA,MAAMM,oBAAoB,GAAGN,UAAU,CAACI,SAAS,CAAE,sBAAuB,CAAC;EAE3E,IAAIG,IAAI,GAAGR,KAAK,CAACS,OAAO,CAAC,CAAC;EAC1B;EACAD,IAAI,GAAG,IAAAE,mBAAU,EAAEF,IAAK,CAAC;EACzBA,IAAI,GAAG,IAAAG,6BAAoB,EAAEH,IAAK,CAAC;;EAEnC;EACA,MAAMI,aAAa,GAAGL,oBAAoB,GAAG,EAAE,GAAG,IAAAM,8CAAqB,EAAEL,IAAK,CAAC;EAE/E,MAAMM,sBAAsB,GAAG,IAAAC,0CAAiB,EAAEP,IAAI,EAAEI,aAAa,EAAEN,OAAO,EAAEJ,aAAa,EAAEK,oBAAqB,CAAC;EAErH,MAAMS,cAAc,GAAG,IAAAC,qDAA4B,EAAEH,sBAAuB,CAAC;EAC7E,IAAAI,2CAAkB,EAAEF,cAAe,CAAC;;EAEpC;AACD;AACA;AACA;EACC,OAAO,IAAAG,YAAI,EAAE,IAAAC,6CAAoB,EAAEJ,cAAc,EAAE,CAAE,CAAC,EAAE,EAAG,CAAC;AAC7D;AAAC,IAAAK,QAAA,GAAAC,OAAA,CAAAxB,OAAA,GAEcC,4BAA4B","ignoreList":[]}